Swell-noise attenuation: A deep learning approach

Abstract

Noise attenuation for ordinary images using machine learning technology has achieved great success in the computer vision field. However, directly applying these models to seismic data would not be effective since the evaluation criteria from the geophysical domain require a high-quality visualized image and the ability to maintain original seismic signals from the contaminated wavelets. This paper introduces an approach equipped with a specially designed deep learning model that can effectively attenuate swell noise with different intensities and characteristics from shot gathers with a relatively simple workflow applicable to marine seismic data sets. Three significant benefits are introduced from the proposed deep learning model. First, our deep learning model doesn't need to consume a pure swell-noise model. Instead, a contaminated swell-noise model derived from field data sets (which may contain other noises or primary signals) can be used for training. Second, inspired by the conventional algorithm for coherent noise attenuation, our neural network model is designed to learn and detect the swell noise rather than inferring the attenuated seismic data. Third, several comparisons (signal-to-noise ratio, mean squared error, and intensities of residual swell noises) indicate that the deep learning approach has the capability to remove swell noise without harming the primary signals. The proposed deep learning-based approach can be considered as an alternative approach that combines and takes advantage of both the conventional and data-driven method to better serve swell-noise attenuation. The comparable results also indicate that the deep learning method has strong potential to solve other coherent noise-attenuation tasks for seismic data.

Application of Noise Attenuation on 2D Shallow Offshore Seismic Reflection Data: A Case Study from the Baltic Sea

“…It is critical to have clean results, as swell noise's high-amplitude characteristics might obscure the seismic signal. It is caused by changes on the ocean surface over extended periods, such as wind-driven longitudinal sea surface waves and dynamic pressure variations along the streamer [13]. A bandpass filter is not recommended to remove swell noise as it could hurt the seismic signal.…”

Machine-learning Based Noise Attenuation of Field Seismic Data using Noise Data Acquisition

“…탄성파 자료에 기록되는 잡음은 선박 소음, 해류의 흐름이나 파도, 장비 운용 등으로 인해 발생한 무작위 잡음 과 다중 반사파(multiple), 공기파(air wave), 표면파(surface wave) 등과 같은 일관성 잡음이 있다 (Ebadi, 2017;Hlebnikov et al, 2021). 탄성파 탐사를 수행하는 과정에서 잡음이 발 생하는 요인을 완전히 억제하는 것은 매우 어렵고 탐사환 경에 따라 상이하기 때문에 탄성파 자료마다 서로 다른 잡 음특성을 가지고 있다 (Kragh and Christie 2002;Nasser et al, 2016;Waage et al, 2019) (Li et al, 2018;Zhao et al, 2019;Liu et al, 2018;Jun et al, 2020)…”

Improved Low-Rank Tensor Approximation for Seismic Random Plus Footprint Noise Suppression

“…Typical DL networks include convolutional neural networks (CNNs) [27]- [30], 3-D denoising CNNs (3D-DnCNNs) [31], [32], deep convolutional autoencoders (DCAEs) [33], [34], 3-D DCAEs [35], [36], and tensor DL (TDL) methods [37], [38]. Other areas of open research include utilizing DL for the suppression of erratic noise [39], coupled noise [41]- [44], swell noise [45], [46], ground-roll noise [47]- [49], and desert noise [50], [51]. However, no DL methods are currently deployed in the geophysics community to assist with suppressing acquired footprints, since the collection of footprints and their clean counterparts is a nontrivial task.…”